Created by: qingqing01

Fix https://github.com/PaddlePaddle/Paddle/issues/5114

some enhancements will be done in next PR.

• Now set the cell state grad to zero to keep the same with the old framework, will support to non-zero cell state gradient.
• Support initial hidden state and cell state.
• In this PR, use the fixed activations (Sigmoid and Tanh) since there is a bug for activation function pointer. Will support to activations specified by users.